Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 72265
    Prev
    Next
    INDEX
    Explanations

    assessment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     taskId
    -0.07
    _args
    -0.07
    =color
    -0.07
    ered
    -0.06
     ParseException
    -0.06
    ских
    -0.06
    meer
    -0.06
    чив
    -0.06
    mes
    -0.06
     sigma
    -0.06
    POSITIVE LOGITS
    Large
    0.07
    azole
    0.06
    因
    0.06
     exhaustive
    0.06
     adresse
    0.06
     vibration
    0.06
     rack
    0.06
    ahl
    0.06
    BIND
    0.06
     syst
    0.06
    Activations Density 0.009%

    No Known Activations